# LTX-2.3 22B Video Trainer API

> Traenálann sé LoRA LTX-2.3 22B le haghaidh stíleanna agus éifeachtaí físeáin saincheaptha, le fuaim roghnach

Traenálann sé LoRA ar an tsamhail LTX-2.3 22B le haghaidh stíleanna agus éifeachtaí saincheaptha ó zip d’fhíseáin nó d’íomhánna, agus 10 gcomhad nó níos mó inmhianaithe. Raontaíonn `number_of_steps` ó 100 go 6000 (réamhshocrú 2000), is é 25 an réamhshocrú do `frame_rate`, agus is é 0.5 an réamhshocrú do `first_frame_conditioning_p`. Cuireann `with_audio` traenáil fuaime i bhfeidhm nó díchumasaíonn sé í, agus rialaíonn `generate_audio_in_validation` fuaim sna réamhamhairc.

- Model id: `ltx23-video-trainer`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0048 / step (cheapest run $9.60 (9600 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-video-trainer`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-video-trainer`
- Docs page: https://doitong.com/ga/developers/models/ltx23-video-trainer

## Pricing

Price: **$0.0048 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $9.60 = 9600 API credits (2000 steps × 4.8 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/ltx23-video-trainer` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | URL cartlainne ZIP do thacar sonraí ina bhfuil íomhánna amháin nó físeáin amháin; ní thacaítear le tacair mheasctha meán. Díriú ar 10 gcomhad nó níos mó, agus bailiúchán níos mó más féidir. Is iad na síntí inghlactha .png, .jpg, .jpeg d’íomhánna agus .mp4, .mov, .avi, .mkv d’fhíseáin. Féadfaidh comhaid téacs roghnacha fotheideal a bheith in éineacht leis na meáin, agus ainm gach comhaid fotheidil comhoiriúnach le hainm an chomhaid meáin ghaolmhair. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rang oiriúnaithe LoRA, a mhalartaíonn tomhaltas cuimhne méadaithe ar acmhainn níos mó de réir mar a ardaíonn an socrú. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Líon iomlán na gcéimeanna oiliúna. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Ráta foghlama optamaithe, a chothromaíonn luasghéarú féideartha san oiliúint leis an mbaol rófheistithe nuair a mhéadaítear é. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Líon frámaí gach sampla oiliúna. Caithfidh fuílleach 1 a bheith ann nuair a roinntear an líon ar 8; mar shampla 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Ráta fráma spriocfhíseáin, tomhaiste i bhfrámaí sa soicind. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Taifeach na hoiliúna. Méadaíonn méadú an taifigh riachtanais chuimhne. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Cóimheas gnéithe na hoiliúna. |
| `trigger_phrase` |  | string | no | `` |  | Frása gníomhachtaithe stíle LoRA, curtha isteach ag tús na bhfotheideal le linn na hoiliúna. |
| `auto_scale_input` |  | boolean | no | `false` |  | Coigeartú uathoibríoch físeáin chun an FPS agus líon frámaí iarrtha a mheaitseáil nuair a chumasaítear é; fanann tacair sonraí íomhánna gan athrú. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Scoilteadh radharcanna d’fhíseáin a sháraíonn tairseach faid, cumasaithe nuair atá sé true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Truicear scoilteadh radharcanna léirithe mar fhad i soicindí: ní scoiltear ach físeáin atá níos faide ná an tairseach. |
| `debug_dataset` |  | boolean | no | `false` |  | Mód iniúchta réamhphróiseála chun físeáin, íomhánna agus fotheidil a sheiceáil roimh rith iomlán oiliúna. Má chumasaítear é, cuireann an traenálaí an tacar sonraí oiliúna próiseáilte ar ais i gcartlann is féidir a íoslódáil lena athbhreithniú de láimh. |
| `with_audio` |  | boolean \| null | no |  |  | Roghnaigh True chun oiliúint fuaime a chur i bhfeidhm taobh le hoiliúint físe, nó False chun fuaim a eisiamh. Má fhágtar an socrú ag a réamhshocrú, None, déantar an rogha go huathoibríoch bunaithe ar cibé an bhfuil fuaim sna físeáin soláthraithe. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalú buaicamplitiúide, molta chun leibhéil fuaime a choinneáil comhsheasmhach ar fud an tacair sonraí trí na buaiceanna a thabhairt chuig leibhéal coiteann. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Caomhnú tuinairde nuair atá fad na fuaime agus an fhíseáin éagsúil: úsáideann cumasaithe síneadh nó comhbhrú ama; úsáideann díchumasaithe bearradh nó stuáil chiúnais ina ionad. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Feabhsaigh feidhmíocht íomhá-go-físeán trí mhinicíocht choinníollú an chéad fhráma in oiliúint a mhéadú; socraíonn an luach seo an dóchúlacht sin. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Liosta leideanna bailíochtaithe oiliúna, agus caithfidh íomhánna a bheith i ngach ionchur ann nó gan íomhánna a bheith i ngach ceann. |
| `validation[].prompt` |  | string | yes |  |  | Leid a úsáidtear le linn bailíochtaithe. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Íomhá le haghaidh bailíochtú íomhá-go-físeán, ceadaithe ach amháin má tá íomhá i ngach ionchur bailíochtaithe eile freisin. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Leid dhiúltach a chuirtear i bhfeidhm le linn bailíochtaithe. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Líon frámaí gach físeáin bhailíochtaithe. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Ráta fráma físeáin spriocbhailíochtaithe, tomhaiste i bhfrámaí sa soicind. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Taifeach a úsáidtear le linn bailíochtaithe. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Cóimheas gnéithe a úsáidtear le linn bailíochtaithe. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Scála Spatio-Temporal Guidance (STG), le 1.0 molta agus 0.0 ag casadh STG as. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | Rialaíonn sé cibé an bhfuil fuaim ghinte i samplaí bailíochtaithe. |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ltx23-video-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx23-video-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx23-video-trainer", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "ltx23-video-trainer",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ltx23-video-trainer",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 9600,
    "usd": "9.60",
    "charged": 9600,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "debug_dataset": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} \| null | URL d’aon fhíseáin bhailíochtaithe atá ar fáil. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL do mheáchain LoRA oilte i bhformáid .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Cumraíocht le haghaidh socrú an chríochphointe tátail. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Cartlann dífhabhtaithe in-íoslódáilte a thugtar ar ais amháin d’ionchuir a bhfuil `debug_dataset` cumasaithe iontu; tá an tacar sonraí oiliúna réamhphróiseáilte inti, lena n-áirítear fuaim agus físeán díchódaithe. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-video-trainer
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=ltx23-video-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-video-trainer